{rfName}
In

Indexed in

License and use

Citations

63

Altmetrics

Grant support

This work has been supported by projects BIBECA (RTI2018-101248-B-I00 MINECO/FEDER), TRESPASS (MSCA-ITN-2019-860813), PRIMA (MSCA-ITN-2019860315), and Accenture. I. Serna is supported by a research fellowship from the Spanish CAM.

Impact on the Sustainable Development Goals (SDGs)

Analysis of institutional authors

Serna, ICorresponding AuthorPeria, AAuthorMorales, AAuthorFierrez, JAuthor

Share

Publications
>
Proceedings Paper

InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics

Publicated to:Proceedings - International Conference on Pattern Recognition. 3720-3727 - 2021-01-01 (), DOI: 10.1109/ICPR48806.2021.9412443

Authors: Serna, Ignacio; Peria, Alejandro; Morales, Aytharni; Fierrez, Julian

Affiliations

Univ Autonoma Madrid, Sch Engn, Madrid, Spain - Author

Abstract

This work explores the biases in learning processes based on deep neural network architectures. We analyze how bias affects deep learning processes through a toy example using the MNIST database and a case study in gender detection from face images. We employ two gender detection models based on popular deep neural networks. We present a comprehensive analysis of bias effects when using an unbalanced training dataset on the features learned by the models. We show how bias impacts in the activations of gender detection models based on face images. We finally propose Inside Bias, a novel method to detect biased models. InsideBias is based on how the models represent the information instead of how they perform, which is the normal practice in other existing methods for bias detection. Our strategy with InsideBias allows to detect biased models with very few samples (only 15 images in our case study). Our experiments include 72K face images from 24K identities and 3 ethnic groups.

Keywords

Gender equality

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal Proceedings - International Conference on Pattern Recognition due to its progression and the good impact it has achieved in recent years, according to the agency Scopus (SJR), it has become a reference in its field. In the year of publication of the work, 2021, it was in position , thus managing to position itself as a Q2 (Segundo Cuartil), in the category Computer Vision and Pattern Recognition.

From a relative perspective, and based on the normalized impact indicator calculated from World Citations from Scopus Elsevier, it yields a value for the Field-Weighted Citation Impact from the Scopus agency: 2.95, which indicates that, compared to works in the same discipline and in the same year of publication, it ranks as a work cited above average. (source consulted: ESI Nov 14, 2024)

This information is reinforced by other indicators of the same type, which, although dynamic over time and dependent on the set of average global citations at the time of their calculation, consistently position the work at some point among the top 50% most cited in its field:

  • Field Citation Ratio (FCR) from Dimensions: 19.32 (source consulted: Dimensions Jun 2025)

Specifically, and according to different indexing agencies, this work has accumulated citations as of 2025-06-20, the following number of citations:

  • WoS: 25
  • Scopus: 38
  • Open Alex: 49
  • OpenCitations: 33

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2025-06-20:

  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 43 (PlumX).
Continuing with the social impact of the work, it is important to emphasize that, due to its content, it can be assigned to the area of interest of ODS 5 - Gender Equality, with a probability of 50% according to the mBERT algorithm developed by Aurora University.

Leadership analysis of institutional authors

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (DE LA SERNA CABELLO, JOSE IGNACIO) and Last Author (FIERREZ AGUILAR, JULIAN).

the author responsible for correspondence tasks has been DE LA SERNA CABELLO, JOSE IGNACIO.